---
title: LLM Image
description: Turn a text prompt into a generated image URL for your workflow result.
source: https://www.edgaze.ai/docs/builder/nodes/llm-image
section: builder
---
# LLM Image

> Turn a text prompt into a generated image URL for your workflow result.

## Overview

LLM Image creates visuals from a prompt using Gemini or OpenAI image models. Default is Nano Banana 2 (Gemini 3.1 Flash Image).

It works best after upstream steps have already shaped a clear, specific prompt , not raw vague customer input.

```docsgraph
llm-image
```

## Ports

- **Input , Prompt:** The image description, usually polished text from an upstream LLM or input block.
- **Output , Image URL:** A link to the generated image for display or downstream use.

## Inspector

- **Prompt:** Fallback description when Prompt input is not connected.
- **Model:** Image provider and generation behavior.
- **Aspect ratio:** Frame shape , Gemini uses this directly; OpenAI maps to the nearest supported shape.
- **Quality:** Low, medium, or high , applies to OpenAI image models only; ignored for Gemini.

## Tips

- Refine the prompt upstream before image generation , this block is for output, not thinking.
- Pick aspect ratio to match the product (square, landscape, portrait).
- Treat image generation as a late-stage step in the graph.
- Confirm the run modal shows images correctly when Image URL feeds Workflow Output.

## Related

- [Workflow Studio](/docs/builder/workflow-studio)